© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1783
    Prev
    Next
    INDEX
    Explanations

    code context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    0.63
     etc
    0.56
     i
    0.53
     adipisicing
    0.53
    ug
    0.53
    これで
    0.53
    cf
    0.53
     at
    0.52
    nul
    0.51
    pond
    0.49
    POSITIVE LOGITS
    IsResolver
    0.86
    த்ரே
    0.83
     ক্ষত্রিয়
    0.82
    <unused829>
    0.79
    <unused2175>
    0.79
     فتح
    0.78
    䪱
    0.78
     ইলেক্ট্রোলাই
    0.77
    штейн
    0.77
    <unused1279>
    0.76
    Activations Density 0.002%

    No Known Activations